mlsanityData to 7 Oct 2026

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

arXiv 2604.05014 ↗First posted 6 Apr 2026cs.RO cs.AI cs.CVcited by 103

On the map: World models → Embodied and robot world models

also in 2 more
Abstract (arXiv)

Building generalist embodied agents requires integrating perception, language understanding, and action, which are core capabilities addressed by Vision-Language-Action (VLA) approaches based on multimodal foundation models, including recent advances in vision-language models and world models. Despite rapid progress, VLA methods remain fragmented across incompatible architectures, codebases, and evaluation protocols, hindering principled comparison and reproducibility. We present StarVLA, an open-source codebase for VLA research. StarVLA addresses these challenges in three aspects. First, it provides a modular backbone--action-head architecture that supports both VLM backbones (e.g., Qwen-VL) and world-model backbones (e.g., Cosmos) alongside representative action-decoding paradigms, all under a shared abstraction in which backbone and action head can each be swapped independently. Second, it provides reusable training strategies, including cross-embodiment learning and multimodal co-training, that apply consistently across supported paradigms. Third, it integrates major benchmarks, including LIBERO, SimplerEnv, RoboTwin~2.0, RoboCasa-GR1, and BEHAVIOR-1K, through a unified evaluation interface that supports both simulation and real-robot deployment. StarVLA also ships simple, fully reproducible single-benchmark training recipes that, despite minimal data engineering, already match or surpass prior methods on multiple benchmarks with both VLM and world-model backbones. To our best knowledge, StarVLA is one of the most comprehensive open-source VLA frameworks available, and we expect it to lower the barrier for reproducing existing methods and prototyping new ones. StarVLA is being actively maintained and expanded; we will update this report as the project evolves. The code and documentation are available at https://github.com/starVLA/starVLA.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 75 of its 77 references that are in the map. First posted on arXiv 6 Apr 2026.

Builds on

75 of 77 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?17 Mar
  2. 2026World Action Models are Zero-shot Policies17 Feb
  3. 2026WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL15 Feb
  4. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning12 Feb
  5. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos6 Feb
  6. 2026Causal World Modeling for Robot Control29 Jan
  7. 2025Evaluating Gemini Robotics Policies in a Veo World Simulator11 Dec
  8. 2025GigaWorld-0: World Models as Data Engine to Empower Embodied AI25 Nov
  9. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulation11 Oct
  10. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning11 Jun
  11. 2025FLARE: Robot Learning with Implicit World Modeling21 May
  12. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2023Segment Anythingcited by 8,158
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2025Qwen2.5-VL Technical Reportcited by 5,418
  9. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  10. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  11. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  12. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
38 more
  1. 2025Qwen3-VL Technical Reportcited by 2,534
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  5. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  6. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  7. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  8. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  9. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  10. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  11. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  12. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  13. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  14. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  15. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  16. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  17. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  18. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  19. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  20. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  21. 2024Latent Action Pretraining from Videoscited by 302
  22. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  23. 2025LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelscited by 278
  24. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  25. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  26. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  27. 2025Seedance 1.0: Exploring the Boundaries of Video Generation Modelscited by 247
  28. 2022Masked Visual Pre-training for Motor Controlcited by 246
  29. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  30. 2025EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Videocited by 191
  31. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  32. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 159
  33. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  34. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 138
  35. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  36. 2025EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videoscited by 116
  37. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representationscited by 115
  38. 2025ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Modelcited by 112

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 103.

103 papers.

Sort:

By area:

  1. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  2. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 47
  3. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
  4. 2026Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agentscited by 37
  5. 2026RLDX-1 Technical Reportcited by 25
  6. 2026Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stackcited by 20
  7. 2026EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policiescited by 18
  8. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  9. 2026JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modelingcited by 12
  10. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 10
  11. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesiscited by 10
  12. 2026Long-Horizon Manipulation via Trace-Conditioned VLA Planningcited by 9
38 more
  1. 2026TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAMcited by 9
  2. 2026LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulationcited by 9
  3. 2026DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulationcited by 8
  4. 2026Kairos: A Regret-Aware Native World-Action Model Stack for Physical AIcited by 8
  5. 2026DSWAM: A Dual-System World Action Foundation Model for Fine-Grained Robot Manipulationcited by 8
  6. 2026HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation Systemcited by 7
  7. 2026RotVLA: Rotational Latent Action for Vision-Language-Action Modelcited by 7
  8. 2026IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulationcited by 7
  9. 2026Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Actioncited by 7
  10. 2026FrameSkip: Learning from Fewer but More Informative Frames in VLA Trainingcited by 6
  11. 2026Orca: The World is in Your Mindcited by 6
  12. 2026Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Modelscited by 5
  13. 2026LA4VLA: Learning to Act without Seeing via Language-Action Pretrainingcited by 5
  14. 2026Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervisioncited by 5
  15. 2026ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AIcited by 5
  16. 2026Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Modelscited by 5
  17. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
  18. 2026Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulationcited by 4
  19. 2026Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignmentcited by 4
  20. 2026GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulationcited by 4
  21. 2026DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executorscited by 3
  22. 2026Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulationcited by 3
  23. 2026Lngram: N-gram Conditional Memory in Latent Spacecited by 3
  24. 2026TempoVLA: Learning Speed-Controllable Vision-Language-Action Policiescited by 3
  25. 2026Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inferencecited by 3
  26. 2026Towards Backdoor-Based Ownership Verification for Vision-Language-Action Modelscited by 2
  27. 2026PhysBrain 1.0 Technical Reportcited by 2
  28. 2026Bridge-WA: Predicting Where and How the World Changes for Robotic Actioncited by 2
  29. 2026FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Modelscited by 2
  30. 2026HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alonecited by 2
  31. 2026What Matters for Latent Actions in Robot Learningcited by 2
  32. 2026Latent Action as Intention Enables Efficient Future Imagination for World Action Modelscited by 2
  33. 2026GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulationcited by 2
  34. 2026VLA Foundry: A Unified Framework for Training Vision-Language-Action Modelscited by 1
  35. 2026CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchorscited by 1
  36. 2026Geometry Guided Self-Consistency for Physical AIcited by 1
  37. 2026RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learningcited by 1
  38. 2026PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Modelscited by 1

50 most cited of 103 All 103 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systems
  2. 2026Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline
  3. 2025An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
  4. 2026Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
  5. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
  6. 202510 Open Challenges Steering the Future of Vision-Language-Action Models
  7. 2024A Survey on Vision-Language-Action Models for Embodied AI
  8. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model